With the escalating demand for computing power driven by the advancements in deep learning and artificial intelligence (AI), the computing power networks serve as critical infrastructure nowadays. Recently, the emerging blockchain enhanced computing power networks has showed appealing advantages of fair and reliable resource allocation, adaptive and flexible management on heterogeneous computing power network, transparent and trustworthy transactions, thereby alleviating the drawbacks of traditional computing infrastructure. Yet, the efficiency and security concerns associated with blockchain-based transactions are neglected when it is applied to computing power trading scenario. To address these issues, in this paper, we introduces the EFSC (Efficient, Flexible, Secure Computing-power-trading) system, a blockchain and smart contracts-based solution aimed at enhancing the efficiency and security of computing power trading. By leveraging a hybrid mechanism that combines on-chain and off-chain methods and utilizing off-chain transaction channels, the EFSC system achieves high throughput transaction processing while also supporting adjustable on-chain policies. Furthermore, transaction data templates based on the Verifiable Credentials (VC) data model enable flexible computing power transaction patterns, allowing providers to define and register configurable transaction initiation and settlement credential templates. To address transaction security concerns, the system leverages Decentralized Identifiers (DID) for off-chain channel access authentication and utilizes DID and VC mechanisms to facilitate transaction initiation and settlement processing, thereby enhancing the credibility and authenticity of transaction data. The experimental results and analysis demonstrate the effectiveness of proposed system.

The explosion of data over the last decades puts significant strain on the computational capacity of the central processing unit (CPU), challenging online analytical processing (OLAP). While previous studies have shown the potential of using Field Programmable Gate Arrays (FPGAs) in database systems, integrating FPGA-based hardware acceleration with relational databases remains challenging because of the complex nature of relational database operations and the need for specialized FPGA programming skills. Additionally, there are significant challenges related to optimizing FPGA-based acceleration for specific database workloads, ensuring data consistency and reliability, and integrating FPGA-based hardware acceleration with existing database infrastructure. In this study, we proposed a novel end-to-end FPGA-based acceleration system that supports native SQL statements and storage engine. We defined a callback process to reload the database query logic and customize the scanning method for database queries. Through middleware process development, we optimized offloading efficiency on PCIe bus by scheduling data transmission and computation in a pipeline workflow. Additionally, we designed a novel five-stage FPGA microarchitecture module that achieves optimal clock frequency, further enhancing offloading efficiency. Results from systematic evaluations indicate that our solution allows a single FPGA card to perform as well as 8 CPU query processes, while reducing CPU load by 34%. Compared to using 4 CPU cores, our FPGA-based acceleration system reduces query latency by 1.7 times without increasing CPU load. Furthermore, our proposed solution achieves 2.1 times computation speedup for data filtering compared with the software baseline in a single core environment. Overall, our work presents a valuable end- to-end hardware acceleration system for OLAP databases.

With the rapid development of web services, social media has been a prevalent and readily way for people to express themselves and share their daily lives. Consequently, numerous user-generated content is accumulated on social media platforms. These data usually contain rich information and knowledge for users, which is a viable source for user data mining. As one of the prevalent techniques in user data mining, mining personalized topics and discovering user preferences from social media data attract much interest in academic and industrial communities. The emerging Neural Topic Models(NTMs) have recently shown leading performance and scalability by employing neural networks. However, most existing NTMs usually model topics simply from observed document token information and do not explicitly take user preferences into the generative process, which inevitably fails to model personalized topics. To address this issue, we introduce Neural Personalized Topic Model(NPTM), a novel NTM that can discover personalized topics and user preferences. NPTM introduces a novel hybrid generative process for combining user preferences and contextualized document codes in modeling personalized topics. A transformer-based document encoder to obtain contextualized document codes. For user preference modeling, NPTM regards user-related information as trainable user embeddings, further determining user preferences over the topics. Following the proposed hybrid generative process, we present a module-wise asynchronous optimization strategy to get coherent topics and user preferences. Then, we apply our model to two challenging real-world social media post collections and compare them against several baseline methods to verify our contributions. The experimental results demonstrate the effectiveness of the proposed method.

Large-scale knowledge in the artificial intelligence of things (AIoT) field urgently needs effective models to understand human language and automatically answer questions. Pretrained language models achieve state-of-the-art performance on some question answering (QA) datasets, but few models can answer questions on AIoT domain knowledge. Currently, the AIoT domain lacks sufficient QA datasets and large-scale pretraining corpora. In this article, we propose RoBERTa$_{\mathrm AIoT}$to address the problem of the lack of high-quality large-scale labeled AIoT QA datasets. We construct an AIoT corpus to further pretrain RoBERTa and BERT. RoBERTa$_{\mathrm AIoT}$and BERT$_{\mathrm AIoT}$leverage unsupervised pretraining on a large corpus composed of AIoT-oriented Wikipedia webpages to learn more domain-specific context and improve performance on the AIoT QA tasks. To fine-tune and evaluate the model, we construct three AIoT QA datasets based on the community QA websites. We evaluate our approach on these datasets, and the experimental results demonstrate the significant improvements of our approach.

We propose CFS, a distributed file system for large scale container platforms. CFS supports both sequential and random file accesses with optimized storage for both large files and small files, and adopts different replication protocols for different write scenarios to improve the replication performance. It employs a metadata subsystem to store and distribute the file metadata across different storage nodes based on the memory usage. This metadata placement strategy avoids the need of data rebalancing during capacity expansion. CFS also provides POSIX-compliant APIs with relaxed semantics and metadata atomicity to improve the system performance. We performed a comprehensive comparison with Ceph, a widely-used distributed file system on container platforms. Our experimental results show that, in testing 7 commonly used metadata operations, CFS gives around 3 times performance boost on average. In addition, CFS exhibits better random-read/write performance in highly concurrent environments with multiple clients and processes.

Given the explosive growth of scientific information and the fast advancement of research fields, researchers may not be able to find the most promising topics to combine with their current research and may be trapped in a few familiar research topics without creative ideas. Many studies of recommendation system make the effort to address the above problem, but they ignore the different styles of users and generate the recommendation results based on a common strategy. In this paper, we propose a framework to generate the adaptive recommendation results according to the research styles of users. Our framework contains 3 main parts, the research topic ontology construction, trend prediction and recommendation. First of all, the Fun of Academic Research Ontology (FARO), which has the capacity of describing dynamic and static research features and building a social network, is constructed to organize entities about academic research. Secondly, this paper predicts the popularity variation of research topics with the neural network model. Finally, some adaptive topics are recommended to specific researchers according to the evaluation of their research styles. Basically, this paper is inspired by the associative thinking of human brain to combine the advantages of Web knowledge representation language and the neural network to execute the prediction and recommendation. We test our results based on the publication data of IEEE and Springer. The experimental results demonstrate that our prediction model has a good generalization performance. A questionnaire survey is carried out to assess the recommendation results, and the result shows the feasibility of our method.